A Two-Phase Mechanism for Agent's Action Selection in Soccer Simulation

Authors: Vahid Salmani, Mahmoud Naghibzadeh, Farid Seifi, Amirhossein Taherinia

Abstract:

Soccer simulation is an effort to motivate researchers and practitioners to do artificial and robotic intelligence research; and at the same time put into practice and test the results. Many researchers and practitioners throughout the world are continuously working to polish their ideas and improve their implemented systems. At the same time, new groups are forming and they bring bright new thoughts to the field. The research includes designing and executing robotic soccer simulation algorithms. In our research, a soccer simulation player is considered to be an intelligent agent that is capable of receiving information from the environment, analyze it and to choose the best action from a set of possible ones, for its next move. We concentrate on developing a two-phase method for the soccer player agent to choose its best next move. The method is then implemented into our software system called Nexus simulation team of Ferdowsi University. This system is based on TsinghuAeolus[1] team that was the champion of the world RoboCup soccer simulation contest in 2001 and 2002.

Keywords: RoboCup, Soccer simulation, multi-agent environment, intelligent soccer agent, ball controller agent.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1056194

References:

[1] Yao Jinyi, Chen Jiang, (2001). Architecture of TsinghuAeolus, TsinghuAeulos Team Description Paper. available: http://portal.acm.org.
[2] Ehsan Foroughi and Fredrik Heintz, (2001, June 11). Robocup Soccer Server manual 7.07, RoboCup Federation. available: http://sserver.sourceforge.net.
[3] Remco de Boer and Jelle Kok, (2002). The Incremental Development of a Synthetic Multi-Agent System: The UvA Trilearn 2001 Robotic Soccer Simulation Team, MS Thesis. Faculty of Science, University of Amsterdam. available: http://carol.wins.uva.nl/~jellekok/publications/2002/mastersthesis.pdf
[4] Stuart J. Russell and Peter nerving, Artificial Intelligence A modern Approach, Prentice Hall, 1995.
[5] Luís Paulo Reis and Nuno Lau, (2001). FC Portugal Team Description: RoboCup 2000 Simulation League Champion, FC Portugal 2000 Team Description Paper. available: http://www.ieeta.pt/robocup/documents/FCPortugalChampion.ps.zip
[6] Peter Stone and David McAllester, "An Architecture for Action Selection in Robotic Soccer," pp. 1-8. AT&T Labs - Research. Florham Park, NJ, 2001.
[7] Peter Stone, (1998). Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer, PhD Thesis, Computer Science Department, Carnegie Mellon University, Pittsburgh, Available as technical report. Available: http://www.cs.utexas.edu/~pstone/book/
[8] SoccerDoctor v1.0, (2002). Available: http://wrighteagle.org/sim/tools/SoccerDoctor.exe